dsh-think-zh
强制 DeepSeek Harness 的回答与思考使用简体中文
55 results
强制 DeepSeek Harness 的回答与思考使用简体中文
Per-model capability declaration for DeepSeek Harness: reasoning-effort levels (with wire spellings) and request modalities (text/image) for OpenAI-compatible providers — one settings section, no YAML hand-editing.
Reasoning effort settings and per-call subagent model routing for DeepSeek Harness custom providers
Global model request headers plus image input, reasoning, and DeepSeek system-role compatibility for custom providers
DeepSeek Harness composer model seat: model picker plus a three-stop reasoning bar (小难梁 / 梁子 / 梁圣)
DeepSeek Harness 前端插件:梁系强度滑动条 —— 用 6 档滑块替换输入框的模型与推理等级按钮(小难梁/牢梁/梁子/梁圣/梁神/梁祖),悬停时在进度条上方显示对应档位形象图,切换带交叉淡入淡出渐变
Neovim-style TUI for DeepSeek Harness (dsh): nvim renders the terminal, a Node runner bridges DSH agent events over msgpack-RPC — sessions, tool cards, reasoning panel, approvals, markdown tables
CodeBuddy (copilot.tencent.com) provider bundle for DeepSeek Harness (dsh): 18 models (DeepSeek, GLM, Kimi, MiniMax, Hunyuan, auto) with adjustable reasoning efforts, CodeBuddy web search / web fetch backends for the stock dsh tools, and a settings card in the Web UI.
DSH web plugin: 为自定义模型(OpenAI-compatible pi-ai provider)增加思考强度(reasoning effort)配置 —— 设置页新增「思考强度」分区,按模型配置思考级别与线格式、按 provider 配置默认思考强度,直接写入 llm-pi-ai 设置,composer 模型选择器随即生效。
Fold mis-rendered thinking content into collapsible blocks, render mermaid inline, show file-edit diff counts, rewrite composer drafts with the current model, and resume interrupted turns from the send button.
Capability-aware reasoning controls and provider-native Fast mode for the DeepSeek Harness web composer
Reasoning-wait thinking indicator for the DeepSeek Harness web composer
DSH「蓝色大肥鱼·智商鉴定中心」:从放鱼时刻起对全部运行中会话的 thinking(reasoning)内容做短语检测统计,含思考块数、思考字符数、偷吃/头脑大开词/吃瓜词命中与梁圣/梁子判定;侧边栏按钮 + 可拖拽悬浮窗,检测词可自由增删
Animated reasoning-level slider for DeepSeek Harness model selection.
DSH web 插件:折叠思考过程直接输出回答内容;在会话输入框上方增加会话活动状态条,展示 Think / Edit / Bash / Read,可展开与收起。 / DSH web plugin: folds the thinking process so answers render directly, and adds a session-activity status bar above the composer showing Think / Edit / Bash / Read, expandable and collapsible.
DeepSeek Harness plugin with two default model-and-reasoning shortcuts above the composer and optional Settings customization.
DSH Web GUI 模型能力配置:在「设置 → 模型」的模型目录编辑器内,为每个已配置的模型直接设置是否支持图像与思考等级(reasoning efforts),写入 llm-pi-ai 设置命名空间。
Side chat panel for the DeepSeek Harness web GUI: hover-to-open hot zone, right details-column chat, model/effort controls, selection-to-send, streaming replies with collapsible reasoning and markdown tables
Sliding-rheostat theme: model + reasoning-effort driven accent, glow and gear dock for the dsh web GUI
Message edit / regenerate for DSH Web: inline edit of assistant replies (text + reasoning), regenerate replies, and user-message edit — a Cordis host plugin serving /api/msg-edit/* plus a dsh.client UI plugin contributing to the assistant action strip.
Shows the selected model provider's account balance next to the composer model seat once a model and reasoning effort are selected.
Provider-folded model selector for the DSH Web composer with catalog-driven reasoning effort choices.
Limit the expanded thinking block to a bounded scroll window in the DSH web conversation.
DeepSeek Harness 插件:在 Web GUI 中选择模型的推理程度(reasoning effort)。按当前模型的适配器目录展示可选档位(如 Off / High / Max),一键写入会话的模型选择。